Artificial Intelligence (AI) is being used more and more across different applications, with the medical device industry being no exception. As AI is popping up more in the medical field, we can start to analyze the risks and benefits of AI in healthcare.
We see examples in everyday life. A good example of this is the Nest devices for home automation. These devices use AI to determine things like personal preferences and adjustments for conditions. Google Assistant on your smartphone is another good example, providing you with helpful “just in time” information based on what it learns about your preferences. Self-driving cars are another example of AI in action.
AI has proven to be quite the disruptor – meaning it brings about a whole new paradigm for how things work or how we get tasks done. Let’s take a look at the benefits of AI in healthcare and how medical devices are creating a new paradigm:
Clinical health data
As health care moves toward adopting digital health, more and more data will be generated. However, clinicians are currently overloaded and have a hard time digesting the data currently available to them. Providing them with more raw data will only serve to overwhelm them further and not be useful.
An advancement and benefit of AI in healthcare that has helped are smart algorithms that can read that data for clinicians or patients. The AI can provide insights by processing the data and may even notice patterns that are not immediately obvious to the human eye. It’s a more efficient way of getting actionable data.
A good example of this is devices that monitor glucose levels. They can notice trends like whether glucose is heading up or down. Rather than providing raw readings, it can send alerts to notify the user of key trends, allowing them to take prompt action. It may even automatically adjust insulin dosages to respond to key glucose information.
Medtronics’ Continuous Glucose Monitoring device (CGM) is a good example that does all of those things. There are other companies developing new digital health technology for other monitored conditions that will work with similar principles.
[bctt tweet=”Smart AI algorithms are helping advance clinical monitoring” username=”galendata”]
Processing large data sets for diagnosis
The processing of large amounts of data is another benefit of AI in healthcare and an area where AI is disrupting the medical device world. Some conditions are very hard to diagnose, such as metastatic cancers. AI-powered devices or algorithms can access a wider range of data and seek out patterns or other factors that can be useful for diagnosis.
For example, there is a recent NIH study into the diagnosis of metastatic breast cancers using artificial intelligence. They found that the AI technology was as accurate as 99%, even detecting “micrometastases,” which are very difficult for human pathologists to detect.
The figure around 99% is far superior to what the human eye has been achieving, especially when under time pressure. Another study found that, when diagnosing on their own (without the aid of AI), pathologists miss up to 60% of small tumors, especially when they are rushed for time. This is another way in which AI can prove to be a lifesaver when used with medical devices. Early detection and appropriate treatment are always preferable for better health outcomes.
Help with training or diagnosis in under-resourced areas
Some countries or areas have particular challenges with either being under-resourced with qualified clinicians or have less access to skilled training. In these countries, misdiagnosis or completely missing a problem tends to be more common. Another study of the use of high-resolution microendoscope images for diagnosis of esophageal tumors found it to be highly effective, and to show great promise for those countries low on resources.
AI systems are by no means perfect, but even where they can’t beat the human operator, they often improve outcomes when used in conjunction with the human clinician. As the technology continues to advance, we expect to see more benefits of AI in healthcare diagnostics.
NASA’s Human Research Program is developing a platform that uses machine learning to identify a wide variety of issues that are seen as critical issues for space flight. For example, things like bone density, intracranial pressure, and cardiovascular pathologies are all important factors to monitor. They’re also developing smart guidance systems that allow relatively untrained astronauts to use ultrasound machines properly. It provides an almost “GPS-like” guidance to astronauts, explaining where to move the probe and how to move it to get good images.
This same technology developed by NASA could again be applied to any under-resourced communities. If the technology is proven accurate, then this could help speed accurate diagnosis in these areas.
Drug development traditionally takes a very long time and often involves several “misses” before companies strike one formula that works. This long development period adds to the high cost of drugs that we see today.
AI is being applied to drug development by helping scientists to identify promising candidates early on. This means they can focus on developing only those that are the most relevant and they can shave years off development.
One example is a partnership between GNS Healthcare and REFS (Reverse Engineering and Forward Simulation) to unlock and analyze complex medical data. They will use patient data to generate new models that help guide researchers to find hidden drivers in cancer progression.
Another example is GSK and Exscientia partnering and discovering novel and selective small molecules for up to 10 disease-related targets. The aim is also to make the early stages of drug discovery more efficient.
In fact, if we look at the entire development cycle for pharmaceuticals, AI can have an impact at every phase. For patients who have exhausted all other treatments for their condition, a clinical trial may be their last hope. One of the major challenges is finding and being accepted onto a relevant clinical trial. Currently, patients have to scour the government database of clinical trials themselves, unless their physician or someone they know happens to already know of a trial for them. They then go through an exhaustive process of evaluations for inclusion and exclusion criteria. (See the process map below from CBC Insights).
The many benefits of AI in healthcare doesn’t stop at physicians, but can also be applied to patient impact. Patients who are looking for clinical trials by smoothing out the process of finding a trial. Many patients miss out due to enrollment difficulties, so AI can help by recommending trials that are a match for patient condition or symptoms. It could extract data from the patient’s medical records to come up with recommendations, saving the patient hours of painstaking combing for a trial.
AI in medical device design
Another application of AI is to monitor and assess information that is pertinent to a medical device design in the hopes of creating improved designs in the future. For example, AI can monitor things like adverse events, complaints and related conditions, looking for patterns that can be useful.
An algorithm may even be able to make design suggestions in the future or at least point out risk in designs. For example, AI can scan databases and learn that particular features have been troublesome for other medical devices.
AI is one of the biggest disruptors of our time but also a huge asset to medical device companies. Of course, as a new technology, there are still some issues that will need to be worked out in the future.
For example, AI runs by accessing data. The more it can get hold of, the more it learns. In the healthcare world, different systems of data don’t “talk” with one another. Devices that are powered by AI need to get around accessing data from multiple treatment providers while remaining compliant with HIPAA regulations.
Despite these sorts of challenges, use of AI continues to progress and benefits of AI in healthcare provide a promising future. We expect to see it become something of a norm within the medical device world in the near future.